Intel · Xe2 (Battlemage), BMG-G31

Best AI Models for Intel Arc Pro B65 (32 GB)

Runs 27–31B and 35B MoE models well; 70B doesn't fit in 32 GB.

32 GB GDDR6608 GB/s99 TFLOPS FP16200 WXe2 (Battlemage), BMG-G31 2026

B60-class compute with B70 memory — 32 GB at 608 GB/s for about $910, so capacity per dollar is its whole argument. Add-in-board partners only; Intel ships no reference card and set no MSRP.

What LLMs can the Arc Pro B65 run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s	66.5 tok/s	Q4_K_M · 16.5 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.1 t/s	75.1 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 57.0 t/s	57.0 tok/s	Q4_K_M · 22.0 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s	66.5 tok/s	Q4_K_M · 16.5 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.1 t/s	75.1 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s	66.5 tok/s	Q4_K_M · 16.5 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.1 t/s	75.1 tok/s	Q4_K_M · 13.1 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Math Score	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 57.0 t/s	57.0 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s	66.5 tok/s	overall	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 66.0 t/s	66.0 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 93.3 t/s	93.3 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 75.1 t/s	75.1 tok/s	Q4_K_M · 13.1 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s	66.5 tok/s	Q4_K_M · 16.5 GB
4	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 66.0 t/s	66.0 tok/s	Q4_K_M · 19.3 GB
5	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 61.1 t/s	61.1 tok/s	Q4_K_M · 19.4 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 17.5 t/s	17.5 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 66.5 t/s	66.5 tok/s	Q4_K_M · 16.5 GB
4	Gemma 3 27B ITGoogle Q4_K_M · 21.7 GB · 16.8 t/s	16.8 tok/s	Q4_K_M · 21.7 GB
5	MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 62.3 t/s	62.3 tok/s	Q4_K_M · 22.1 GB

See all 346 models on the Arc Pro B65 →Best quant that fits · speeds estimated on this card

About the Arc Pro B65

The Arc Pro B65 runs 27–31B and 35B MoE models well. Xe2 (Battlemage), BMG-G31 generation, released 2026.

GenerationXe2 (Battlemage), BMG-G31released 2026

Arc Pro B65 strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 57.0 tok/s in 22 GB
Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 14.1 GB free

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 32 GB here
Slow prompt reading: A 4K-token prompt on Qwen3.8 27B waits 12.8 s for the first token
oneAPI, not CUDA: No FP8 or NVFP4 weights and no vLLM AWQ or GPTQ; use GGUF builds

Arc Pro B65 tokens per second by model size

Output speed depends on memory bandwidth (608 GB/s). Grey rows need more than 32 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
47.8tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
32.0tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
17.5tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
57.0tok/s
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 346 models on the Arc Pro B65

Featured only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with Intel Arc Pro B65 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen3.8 27B27.8BVisionFunctions Q4_K_M·17.5 t/s	Q4_K_M	17.9 GB56%	17.5 t/s	262K	B57, Decent
Qwen3.6 35B A3B36.0BVisionFunctions Q4_K_M·57.0 t/s	Q4_K_M	22.0 GB69%	57.0 t/s	262K	A82, Runs well
Gemma 4 26B A4B IT25.8BVisionFunctions Q4_K_M·66.5 t/s	Q4_K_M	16.5 GB52%	66.5 t/s	262K	S85, Runs great
NVIDIA Nemotron 3.5 Lightning 30B A3B BF1631.6BChatFunctions Q4_K_M·66.0 t/s	Q4_K_M	19.3 GB60%	66.0 t/s	262K	S85, Runs great
Muse Glimmer 30B29.8BVision Q4_K_M·16.6 t/s	Q4_K_M	19.6 GB61%	16.6 t/s	131K	B56, Decent
Gemma 4 31B IT31.3BVisionFunctions Q4_K_M·14.9 t/s	Q4_K_M	21.7 GB68%	14.9 t/s	262K	B55, Decent
GLM 4.7 Flash31.2BChatFunctions Q4_K_M·52.6 t/s	Q4_K_M	19.9 GB62%	52.6 t/s	203K	A81, Runs well
Flint39.8BChatFunctions Q4_K_M·67.5 t/s	Q4_K_M	25.0 GB78%	67.5 t/s	262K	S85, Runs great
MiniCPM V 4.7 35B A3B35.2BVisionFunctions Q4_K_M·62.3 t/s	Q4_K_M	22.1 GB69%	62.3 t/s	262K	A84, Runs well
LFM2.5 24B A2B24.0BChatFunctions Q4_K_M·76.9 t/s	Q4_K_M	15.0 GB47%	76.9 t/s	131K	S87, Runs great
Sage A1.536.0BChatVisionCodeFunctions Q4_K_M·57.0 t/s	Q4_K_M	22.0 GB69%	57.0 t/s	262K	A82, Runs well
JEV 27B VL27.8BVisionFunctions Q4_K_M·17.5 t/s	Q4_K_M	17.9 GB56%	17.5 t/s	262K	B57, Decent
GPT OSS 20B20.9BChatFunctions Q4_K_M·75.1 t/s	Q4_K_M	13.1 GB41%	75.1 t/s	131K	S86, Runs great
Ornith 1.5 35B A3B36.0BChatFunctions Q4_K_M·57.0 t/s	Q4_K_M	22.0 GB69%	57.0 t/s	262K	A82, Runs well
Ling 3.0 Tiny7.9BChatFunctions Q4_K_M·127.0 t/s	Q4_K_M	5.5 GB17%	127.0 t/s	131K	S95, Runs great

Arc Pro B65 specs, power and PSU

Specs

Architecture: Xe2 (Battlemage), BMG-G31
VRAM: 32 GB GDDR6
Memory bandwidth: 608.0 GB/s
FP16 (dense): 98.50 TFLOPS
Tensor cores: 160
TDP: 200 W
Released: 2026-03-25
MSRP: $910

Arc Pro B65 FAQ

What is the largest model the Arc Pro B65 can run?

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB of 32 GB, and runs at about 57.0 tok/s.

Can the Arc Pro B65 run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 32 GB, and it is the best model that runs well on this card.

Can the Arc Pro B65 run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 32 GB on this card.

How many tokens per second does the Arc Pro B65 give?

About 17.5 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 12.8 s on a 4K-token prompt.

What power supply does the Arc Pro B65 need?

Plan a 400 W PSU (2× the 200 W TDP).

Is 32 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 9 coding models that fit, runs at about 18 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Best coding LLMs 24 GB VRAM 48 GB VRAM GPUs with 32 GB or more RTX 5090